NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-10-01KR8Y49ETP9A2ECXNWCA6JA4A
Run Details
Model:
Gemma 4 26B (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 59s
Cost:
$0.002983
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.8722%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly spread the glitter-strewn blueprints across the greasy table, her eyes narrowing at the drawing of a pink inflatable castle. She pointed a laser at the backyard perimeter. "The bounce house is our extraction point," she hissed. Bill stared blankly at a pile of discarded wrapping paper, looking more interested in a stray gummy bear than the mission. He leaned in, his face illuminated by the glow of a nearby nightlight. "What about the silly clown?" he muttered. Molly rolled her eyes, tapping a finger on the schedule of events. "Focus, Bill," she snapped. "Is there cake?" he asked, eyes widening. "Don't touch that!" she warned. The target was the central gift pile, situated precariously near the juice box station. They would enter through the pet door, bypass the magician, and secure the LEGO sets before the cake was served. The distraction would occur during the piƱata incident. She checked her watch, calculating the trajectory of a falling balloon. This wasn't just a heist; it was a tactical assault on childhood joy. They had to be silent, swift, and immune to the allure of chocolate sprinkles. The stakes were high, and the sugar rush was imminent.
created_at
"2026-05-10T12:34:54.051Z"
5/10/2026, 12:34:54 PM
model
"google/gemma-4-26b-a4b-it-20260403"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
275
moderation_latency
(null)
generation_time
178922
tokens_prompt
77
tokens_completion
6797
native_tokens_prompt
82
native_tokens_completion
8758
native_tokens_completion_images
(null)
native_tokens_reasoning
6503
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.00298346
router
(null)
provider_responses
0
endpoint_id
"d71c6981-347d-4622-a86b-2c9e5d0f2c6c"
id
"chatcmpl-RucfFNzAngM4Io4F7A7kQW8x"
is_byok
false
latency
192
model_permaslug
"google/gemma-4-26b-a4b-it-20260403"
provider_name
"DeepInfra"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1778416494-SQBPzROkpPV0CGOPWaD7"
session_id
(null)
api_type
"completions"
id
"gen-1778416494-YzV0B1LOqmRo4EGlDqqf"
upstream_id
"chatcmpl-RucfFNzAngM4Io4F7A7kQW8x"
total_cost
0.00298346
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
100.00%
Dialogue to Total Word Ratio
Ratio: 10.15%, Deviation: 0.15%
neededClean
false
wordsTotal
197
wordsDialogue
20
99.8722%